Search articles, guides, and topics

A navigation guide for AI engineering delivery: RAG knowledge entry points, requirement contracts, AI-TDD Manifest, BMAD/Speckit workflows, delivery gates, and reusable evidence.

A three-part guide for building a knowledge hub RAG assistant, from system boundaries to retrieval implementation, quality evaluation, safety controls, and release evidence.

AI-TDD turns human intent into a Manifest requirement contract, then accepts AI-generated work through evidence chains and Gate verdicts.

Original technical interpretation and selected articles from foreign technology communities to explore best practices in AI engineering

Based on an in-depth analysis of RAG system failure cases in the production environment, we explore the nature of the silent illusion problem, monitoring blind spots, and architectural-level solutions.

Following the data closed loop in Part 7, this article focuses on how to process the screened engineering assets into high-quality SFT samples and connect them to a manageable, evaluable, and iterable training pipeline.

When AI programming assistants become standard equipment, the real competitiveness is no longer whether they can use AI, but whether they can judge, calibrate and constrain the engineering output of AI. This article starts from trust gaps, feedback protocols, evaluation standards and closed-loop capabilities to establish the core framework of "Humans as Coding Mentors".

In-depth exploration of the complete practical path of fine-tuning large language models, from engineering thinking in data preparation to detailed control of model training, reveals the key methodologies that turn general AI into domain experts.

Failure mode analysis based on practical experience of multi-Agent systems, combined with predictive thinking from science fiction literature

What really determines the upper limit of an agent is often not the model itself, but the harness organized around the model. This article is based on LangChain's disassembly of the agent harness, extending my complete understanding of file systems, code execution, context management, verification closed loops and long-term task endurance. It also explains why the focus of AI engineering competition in 2026 is shifting from 'model capabilities' to 'working system design'.

The failure of long-term task agents often does not stem from the model's inability to think, but from the system's failure to design 'handover, recovery, verification, and continuation' as first-class citizens. This article is based on Anthropic's discussion of long-running agent harness, extending my complete views on cross-session execution, state externalization, feature contract, smoke test, browser verification and multi-round execution structure. It also explains why a truly usable agent does not run for a long time at a time, but can catch it round after round.